{ "cells": [ { "cell_type": "markdown", "id": "976841dc", "metadata": {}, "source": [ "## Preparación de un dataset\n", "\n", "Descargamos el dataset y lo preparamos para el entrenamiento. En el caso de ejemplo, usaremos toxic-teenage-relationships, que son frases que describen si un comporamiento es tóxico o sano. Tienen una campo de texto y un campo de etiqueta, que vale 1 si es tóxico y 0 si no lo es. Acumula 267 ejemplos de entrenamiento y 66 para testear." ] }, { "cell_type": "code", "execution_count": 1, "id": "b9a1f255", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'label': 1,\n", " 'text': 'Mi amiga no puede subir videos a tik tok porque su pareja no le deja'}" ] }, "execution_count": 1, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from datasets import load_dataset\n", "data_files = {\"train\": \"train.csv\", \"test\": \"test.csv\"}\n", "dataset = load_dataset(\"toxic-teenage-relationships\", data_files=data_files, sep=\";\")\n", "dataset['train'][100]" ] }, { "cell_type": "markdown", "id": "6d0c740a", "metadata": {}, "source": [ "Una vez cargado el dataset, se crea un tokenizador para procesar el texto e incluir una estrategia para el padding y el truncamiento. Para poder procesar el dataset en un solo paso, se utiliza el método dataset.map para preprocesar todo el dataset." ] }, { "cell_type": "code", "execution_count": 2, "id": "01673605", "metadata": {}, "outputs": [], "source": [ "#en este ejemplo, utilizamos el AutoTokenizer\n", "from transformers import AutoTokenizer\n", "#from transformers import RobertaTokenizer\n", "\n", "tokenizer = AutoTokenizer.from_pretrained(\"PlanTL-GOB-ES/roberta-base-bne\")\n", "\n", "\n", "def tokenize_function(examples):\n", " return tokenizer(examples[\"text\"], padding=\"max_length\", truncation=True)\n", "\n", "\n", "tokenized_datasets = dataset.map(tokenize_function, batched=True)" ] }, { "cell_type": "markdown", "id": "08aacc14", "metadata": {}, "source": [ "Ahora vamos a convertir el dataset en formator de TensorFlow. Para eso usamos DefaultDataCollator, que junta los tensores en un batch para que el modelo se entrene en él. Debemos especificar el argumento return_tensors=\"tf\". \n" ] }, { "cell_type": "code", "execution_count": 3, "id": "4a854ead", "metadata": {}, "outputs": [], "source": [ "from transformers import DefaultDataCollator\n", "data_collator = DefaultDataCollator(return_tensors=\"tf\")" ] }, { "cell_type": "markdown", "id": "06346bc5", "metadata": {}, "source": [ "guardamos los dataset de train y de test\n" ] }, { "cell_type": "code", "execution_count": 4, "id": "698a98ca", "metadata": {}, "outputs": [], "source": [ "train_dataset = tokenized_datasets[\"train\"]\n", "eval_dataset = tokenized_datasets[\"test\"]" ] }, { "cell_type": "markdown", "id": "38a6c521", "metadata": {}, "source": [ "\n", "\n", "En primer lugar, vamos a crear el modelo\n", "\n" ] }, { "cell_type": "code", "execution_count": 5, "id": "843f218d", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "2023-08-29 20:57:53.276031: W tensorflow/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 154404864 exceeds 10% of free system memory.\n", "2023-08-29 20:57:53.624006: W tensorflow/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 154404864 exceeds 10% of free system memory.\n", "2023-08-29 20:57:53.683150: W tensorflow/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 154404864 exceeds 10% of free system memory.\n", "2023-08-29 20:58:02.251496: W tensorflow/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 154404864 exceeds 10% of free system memory.\n", "2023-08-29 20:58:02.566086: W tensorflow/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 154404864 exceeds 10% of free system memory.\n", "Some weights of the PyTorch model were not used when initializing the TF 2.0 model TFRobertaForSequenceClassification: ['roberta.embeddings.position_ids']\n", "- This IS expected if you are initializing TFRobertaForSequenceClassification from a PyTorch model trained on another task or with another architecture (e.g. initializing a TFBertForSequenceClassification model from a BertForPreTraining model).\n", "- This IS NOT expected if you are initializing TFRobertaForSequenceClassification from a PyTorch model that you expect to be exactly identical (e.g. initializing a TFBertForSequenceClassification model from a BertForSequenceClassification model).\n", "Some weights or buffers of the TF 2.0 model TFRobertaForSequenceClassification were not initialized from the PyTorch model and are newly initialized: ['classifier.dense.weight', 'classifier.dense.bias', 'classifier.out_proj.weight', 'classifier.out_proj.bias']\n", "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n" ] } ], "source": [ "import tensorflow as tf\n", "from transformers import TFAutoModelForSequenceClassification\n", "#también tiene una clase propia para el cabezal de clasificación, en este cogemos el general\n", "#from transformers import TFRobertaForSequenceClassification\n", "#Hay dos categorías, así que ponemos 2 etiquetas (0 sano 1 tóxico)\n", "model = TFAutoModelForSequenceClassification.from_pretrained(\"PlanTL-GOB-ES/roberta-base-bne\", num_labels=2, from_pt=\"True\") " ] }, { "cell_type": "markdown", "id": "54d206b4", "metadata": {}, "source": [ "A hora vamos a convertir los datasets tokenizados en datasets de TensorFlow con el método .to_tf_dataset. Las entradas están en columns y la etiqueta en label_cols. El bach size es el número de ejemplos que se introducen en la red para que se entrene cada vez." ] }, { "cell_type": "code", "execution_count": 6, "id": "2ac843c2", "metadata": {}, "outputs": [], "source": [ "tf_train_dataset= train_dataset.to_tf_dataset(\n", "columns=[\"attention_mask\", \"input_ids\"],\n", "label_cols=\"labels\",\n", "shuffle=True,\n", "collate_fn=data_collator,\n", "batch_size=8,\n", ")\n", "tf_validation_dataset= eval_dataset.to_tf_dataset(\n", "columns=[\"attention_mask\", \"input_ids\"],\n", "label_cols=\"labels\",\n", "shuffle=False,\n", "collate_fn=data_collator,\n", "batch_size=8,\n", ")\n" ] }, { "cell_type": "markdown", "id": "d07f651a", "metadata": {}, "source": [ "Compilamos" ] }, { "cell_type": "code", "execution_count": 7, "id": "72e85cab", "metadata": {}, "outputs": [], "source": [ "model.compile(\n", "optimizer=tf.keras.optimizers.Adam(learning_rate=5e-5),\n", "loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n", "metrics=tf.metrics.SparseCategoricalAccuracy(),\n", ")" ] }, { "cell_type": "markdown", "id": "f103f0de", "metadata": {}, "source": [ "## Cross-validation\n", "Se definen los parámetros de K-flod cross valdation en primer lugar. Al ser un dataset pequeño el nmero de \n", "splits será de 3." ] }, { "cell_type": "code", "execution_count": 8, "id": "924886a1", "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import KFold\n", "from keras.callbacks import EarlyStopping\n", "num_splits = 3\n", "kf = KFold(num_splits, shuffle= True, random_state=42)\n" ] }, { "cell_type": "markdown", "id": "651afcdb", "metadata": {}, "source": [ "\n", "Ahora definimos el ciclo de validación cruzada" ] }, { "cell_type": "code", "execution_count": 9, "id": "f96f6bae", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Fold 1\n", "Epoch 1/10\n", "23/23 [==============================] - 1316s 52s/step - loss: 0.6939 - sparse_categorical_accuracy: 0.5506 - val_loss: 0.6605 - val_sparse_categorical_accuracy: 0.7333\n", "Epoch 2/10\n", "23/23 [==============================] - 1170s 51s/step - loss: 0.5338 - sparse_categorical_accuracy: 0.7809 - val_loss: 0.6009 - val_sparse_categorical_accuracy: 0.7222\n", "Epoch 3/10\n", "23/23 [==============================] - 1088s 47s/step - loss: 0.2613 - sparse_categorical_accuracy: 0.9101 - val_loss: 0.7153 - val_sparse_categorical_accuracy: 0.7556\n", "Epoch 4/10\n", "23/23 [==============================] - 1214s 53s/step - loss: 0.1266 - sparse_categorical_accuracy: 0.9663 - val_loss: 1.1409 - val_sparse_categorical_accuracy: 0.6111\n", "Train\n", "Fold 1 - Loss: 0.224392369389534, Accuracy: 0.9269663095474243\n", "Val\n", "Fold 1 - Loss: 0.6009274125099182, Accuracy: 0.7222222089767456\n", "Fold 2\n", "Epoch 1/10\n", "23/23 [==============================] - 1202s 52s/step - loss: 0.3649 - sparse_categorical_accuracy: 0.8547 - val_loss: 0.3039 - val_sparse_categorical_accuracy: 0.8989\n", "Epoch 2/10\n", "23/23 [==============================] - 1202s 53s/step - loss: 0.2095 - sparse_categorical_accuracy: 0.9385 - val_loss: 0.1956 - val_sparse_categorical_accuracy: 0.9326\n", "Epoch 3/10\n", "23/23 [==============================] - 1183s 52s/step - loss: 0.1031 - sparse_categorical_accuracy: 0.9665 - val_loss: 0.1776 - val_sparse_categorical_accuracy: 0.9213\n", "Epoch 4/10\n", "23/23 [==============================] - 1230s 54s/step - loss: 0.0676 - sparse_categorical_accuracy: 0.9832 - val_loss: 0.1551 - val_sparse_categorical_accuracy: 0.9326\n", "Epoch 5/10\n", "23/23 [==============================] - 1094s 48s/step - loss: 0.0161 - sparse_categorical_accuracy: 0.9944 - val_loss: 0.1954 - val_sparse_categorical_accuracy: 0.9438\n", "Epoch 6/10\n", "23/23 [==============================] - 925s 40s/step - loss: 0.0053 - sparse_categorical_accuracy: 1.0000 - val_loss: 0.2280 - val_sparse_categorical_accuracy: 0.9326\n", "Train\n", "Fold 2 - Loss: 0.01458701491355896, Accuracy: 0.994413435459137\n", "Val\n", "Fold 2 - Loss: 0.15508417785167694, Accuracy: 0.932584285736084\n", "Fold 3\n", "Epoch 1/10\n", "23/23 [==============================] - 830s 36s/step - loss: 0.1665 - sparse_categorical_accuracy: 0.9441 - val_loss: 0.0837 - val_sparse_categorical_accuracy: 0.9888\n", "Epoch 2/10\n", "23/23 [==============================] - 665s 29s/step - loss: 0.0383 - sparse_categorical_accuracy: 0.9888 - val_loss: 0.0101 - val_sparse_categorical_accuracy: 1.0000\n", "Epoch 3/10\n", "23/23 [==============================] - 674s 29s/step - loss: 0.0777 - sparse_categorical_accuracy: 0.9888 - val_loss: 0.1603 - val_sparse_categorical_accuracy: 0.9551\n", "Epoch 4/10\n", "23/23 [==============================] - 623s 27s/step - loss: 0.1500 - sparse_categorical_accuracy: 0.9609 - val_loss: 0.3123 - val_sparse_categorical_accuracy: 0.8764\n", "Train\n", "Fold 3 - Loss: 0.07668939232826233, Accuracy: 0.9776536226272583\n", "Val\n", "Fold 3 - Loss: 0.010059510357677937, Accuracy: 1.0\n" ] }, { "ename": "NameError", "evalue": "name 'np' is not defined", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", "Cell \u001b[0;32mIn[9], line 52\u001b[0m\n\u001b[1;32m 49\u001b[0m val_accuracies\u001b[38;5;241m.\u001b[39mappend(val_scores[\u001b[38;5;241m1\u001b[39m])\n\u001b[1;32m 51\u001b[0m \u001b[38;5;66;03m#Calcular las medidas de las métricas\u001b[39;00m\n\u001b[0;32m---> 52\u001b[0m mean_train_loss \u001b[38;5;241m=\u001b[39m \u001b[43mnp\u001b[49m\u001b[38;5;241m.\u001b[39mmean(train_losses)\n\u001b[1;32m 53\u001b[0m mean_train_accuracy \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mmean(train_accuracies)\n\u001b[1;32m 54\u001b[0m mean_val_loss \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mmean(val_losses)\n", "\u001b[0;31mNameError\u001b[0m: name 'np' is not defined" ] } ], "source": [ "#listas para almacenar las métricas en cada fold\n", "train_losses=[]\n", "train_accuracies=[]\n", "val_losses = []\n", "val_accuracies=[]\n", "\n", "for fold, (train_index, val_index) in enumerate(kf.split(train_dataset)):\n", " print (f\"Fold {fold + 1}\")\n", " \n", " #crear conjuntos de entrenamiento y validación para esta iteración\n", " train_fold_dataset = train_dataset.select(train_index)\n", " val_fold_dataset = train_dataset.select(val_index)\n", " \n", " #convertir los datasets a Tensorflow\n", " tf_train_fold_dataset= train_fold_dataset.to_tf_dataset(\n", " columns=[\"attention_mask\", \"input_ids\"],\n", " label_cols=\"labels\",\n", " shuffle=True,\n", " collate_fn=data_collator,\n", " batch_size=8,\n", " )\n", " \n", " tf_val_fold_dataset= val_fold_dataset.to_tf_dataset(\n", " columns=[\"attention_mask\", \"input_ids\"],\n", " label_cols=\"labels\",\n", " shuffle=False,\n", " collate_fn=data_collator,\n", " batch_size=8,\n", " )\n", " \n", " #early-stop\n", " early_stop=EarlyStopping(monitor=\"val_loss\",patience=2,mode=\"auto\", restore_best_weights=True)\n", " \n", " #entrenar el modelo \n", " model.fit(tf_train_fold_dataset, validation_data=tf_val_fold_dataset, epochs=10, callbacks=[early_stop])\n", " \n", " # Evaluar el modelo \n", " train_scores = model.evaluate(tf_train_fold_dataset, verbose=0)\n", " val_scores = model.evaluate(tf_val_fold_dataset, verbose=0)\n", " print(\"Train\")\n", " print(f\"Fold {fold + 1} - Loss: {train_scores[0]}, Accuracy: {train_scores[1]}\")\n", " print(\"Val\")\n", " print(f\"Fold {fold + 1} - Loss: {val_scores[0]}, Accuracy: {val_scores[1]}\")\n", " \n", " # Guardamos las cifras para después hacer la media\n", " train_losses.append(train_scores[0])\n", " train_accuracies.append(train_scores[1])\n", " val_losses.append(val_scores[0])\n", " val_accuracies.append(val_scores[1])\n", " \n", "\n" ] }, { "cell_type": "code", "execution_count": 10, "id": "4113ab57", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Mean Train Loss: 0.1052229255437851, Mean Train Accuracy: 0.9663444558779398\n", "Mean Val Loss: 0.25535703357309103, Mean Val Accuracy: 0.8849354982376099\n" ] } ], "source": [ "import numpy as np\n", "#Calcular las medidas de las métricas\n", "mean_train_loss = np.mean(train_losses)\n", "mean_train_accuracy = np.mean(train_accuracies)\n", "mean_val_loss = np.mean(val_losses)\n", "mean_val_accuracy = np. mean(val_accuracies)\n", "\n", "#Imprimir las medias de las métricas\n", "print(f\"Mean Train Loss: {mean_train_loss}, Mean Train Accuracy: {mean_train_accuracy}\")\n", "print(f\"Mean Val Loss: {mean_val_loss}, Mean Val Accuracy: {mean_val_accuracy}\")" ] }, { "cell_type": "code", "execution_count": null, "id": "0e0dff1a", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.8.13" } }, "nbformat": 4, "nbformat_minor": 5 }